원문정보
초록
영어
As the ubiquitous computing becomes popular, its applications come to real life as a form of a wide variety of ubiquitous decision support systems (UDSS). However, such ubiquity should be supported by prediction capability no matter which kind of contexts users are in. In this sense, context prediction capability, which is to predict future contexts users are going to enter sooner or later, becomes an extremely important part of ubiquitous decision support systems. This study proposes a new breed of context prediction mechanism using the Markov Blanket obtained from General Bayesian Network (GBN) as a main vehicle. To improve the prediction accuracy, ensemble of robust prediction classifiers is suggested on the basis of the GBN Markov Blanket. Three classifiers included in the ensemble mechanism are Bayesian networks, decision classifiers, and an SVM (Support Vector Machine). The proposed GBN Markov blanket-assisted ensemble classifier is applied to a real dataset of location prediction. Results were promising enough to conclude that the proposed ensemble classifier based on the GBN Markov Blanket is worthwhile for being adopted in developing a powerful context prediction purpose UDSS. Practical implications are also discussed with future research issues.
목차
1. Introduction
2. Ensemble methods: Voting and stacking
3. Empirical evaluation
3.1. Data
3.2. Experimental setup
3.3. Results
4. Discussion
5. Concluding remarks
References